Question

我正在尝试在Google合作实验室的Yolo中使用中检测对象。这是我正在执行的代码段，但出现值错误。寻找帮助，在这里停留了一个多星期。

img = plt.imread('/content/drive/My Drive/Social_distance/img.jpg')
imshow(img)
image_shape = float(img.shape[0]), float(img.shape[1])
print(image_shape)
scores, boxes, classes = yolo_eval(yolo_outputs, image_shape=(720,1280))

yolo_eval（）的定义

def yolo_eval(yolo_outputs, image_shape = (720., 1280.), max_boxes=10, score_threshold=.6, iou_threshold=.5):
   print(image_shape)
   box_confidence, box_xy, box_wh, box_class_probs = yolo_outputs
   boxes = yolo_boxes_to_corners(box_xy, box_wh)
   scores, boxes, classes = yolo_filter_boxes(box_confidence, boxes, box_class_probs, threshold = 
   score_threshold)
   boxes = scale_boxes(boxes, image_shape)
   scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold)

   return scores, boxes, classes

这是错误：

   1606   try:
  -> 1607     c_op = c_api.TF_FinishOperation(op_desc)
   1608   except errors.InvalidArgumentError as e:

  InvalidArgumentError: Dimensions must be equal, but are 2 and 80 for 
  'mul_19' (op: 'Mul') with input shapes: [?,?,?,5,2], [?,?,?,5,80].

  During handling of the above exception, another exception occurred:

  ValueError                                Traceback (most recent call last)
  11 frames
  /tensorflow-1.15.2/python3.6/tensorflow_core/python/framework/ops.py in 
  _create_c_op(graph, node_def, inputs, control_inputs)
  1608   except errors.InvalidArgumentError as e:
  1609     # Convert to ValueError for backwards compatibility.
  -> 1610     raise ValueError(str(e))
   1611 
  1612   return c_op

  ValueError: Dimensions must be equal, but are 2 and 80 for 'mul_19' (op: 
  'Mul') with input shapes: [?,?,?,5,2], [?,?,?,5,80].

Answer 1

我怀疑问题来自yolo_filter_boxes()。尝试做这样的事情：

final_yolo_outputs = (yolo_outputs[2], yolo_outputs[0], yolo_outputs[1], yolo_outputs[3])

然后

scores, boxes, classes = yolo_eval(final_yolo_outputs , image_shape=(720,1280))

如果您还可以提供上面所建议的功能的定义，那将是很好的。

ValueError：尺寸必须相等，但输入形状为[？，？，？，5,2]，[？，？，？，5,80]的'mul_18'（op：'Mul'）的尺寸必须为2和80

1 个答案: